Zobrazeno 1 - 10
of 267
pro vyhledávání: '"Coskun, Ayse"'
Systolic arrays are popular for executing deep neural networks (DNNs) at the edge. Low latency and energy efficiency are key requirements in edge devices such as drones and autonomous vehicles. Monolithic 3D (MONO3D) is an emerging 3D integration tec
Externí odkaz:
http://arxiv.org/abs/2401.03585
Autor:
Ullah, Saad, Han, Mingji, Pujar, Saurabh, Pearce, Hammond, Coskun, Ayse, Stringhini, Gianluca
Large Language Models (LLMs) have been suggested for use in automated vulnerability repair, but benchmarks showing they can consistently identify security-related bugs are lacking. We thus develop SecLLMHolmes, a fully automated evaluation framework
Externí odkaz:
http://arxiv.org/abs/2312.12575
In this paper, we focus on temperature-aware Monolithic 3D (Mono3D) deep neural network (DNN) inference accelerators for biomedical applications. We develop an optimizer that tunes aspect ratios and footprint of the accelerator under user-defined per
Externí odkaz:
http://arxiv.org/abs/2203.15874
Autor:
Coskun, Ayse Kubra1 ayse.coskun@yale.edu, Tosun, Sumeyra2, Jiajun Luo3, Yawei Zhang3, Emre, Sukru3, Zimbrean, Paula3
Publikováno v:
Health Behavior & Policy Review. 2024, Vol. 11 Issue 4, p1672-1686. 15p.
Phase Change Memory (PCM) is an attractive candidate for main memory as it offers non-volatility and zero leakage power, while providing higher cell densities, longer data retention time, and higher capacity scaling compared to DRAM. In PCM, data is
Externí odkaz:
http://arxiv.org/abs/2107.11516
Autor:
Salmon, Mandy K., Cohen, William G., Hu, Fengling, Aydin, Adem, Coskun, Ayse K., Schilsky, Michael, Doty, Richard L.
Publikováno v:
In Journal of the Neurological Sciences 15 April 2024 459
Publikováno v:
In Sustainable Computing: Informatics and Systems April 2024 42
Publikováno v:
2021 International Conference on Applied Artificial Intelligence (ICAPAI), 2021, pp. 1-8
Applying machine learning (ML) on multivariate time series data has growing popularity in many application domains, including in computer system management. For example, recent high performance computing (HPC) research proposes a variety of ML framew
Externí odkaz:
http://arxiv.org/abs/2008.10781
Modern cloud services have complex architectures, often comprising many software components, and depend on hundreds of configurations parameters to function correctly, securely, and with high performance. Due to the prevalence of open-source software
Externí odkaz:
http://arxiv.org/abs/2008.08656
Autor:
Camarata, Michelle A., Ala, Aftab, Coskun, Ayse K., Deng, Yanhong, Embel, Veysel K., Gonzalez-Peralta, Regino, Maciejewski, Kaitlin R., Patel, Amar, Rubman, Susan, To, Uyen, Tomlin, Ricarda, Schilsky, Michael L., Zimbrean, Paula C.
Publikováno v:
In Journal of the Academy of Consultation-Liaison Psychiatry March-April 2023 64(2):106-117